February 2026

In a simple gridworld example, everything stays the same except the discount factor γ. Reward for boundary/forbidden: -1 Reward for target: +1 Only γ changes Case 1: γ = 0.9 The agent is long-term oriented. Future rewards are discounted slowly: γ⁵ ≈ 0.59 So even if the agent takes a -1 penalty now (entering a forbidden area), the future reward is still valuable enough to justify it. Result: The optimal policy is willing to take short-term losses to […]

Ver mais

arXiv:2602.17868v1 Announce Type: new Abstract: Developing foundation models for time series classification is of high practical relevance, as such models can serve as universal feature extractors for diverse downstream tasks. Although early models such as Mantis have shown the promise of this approach, a substantial performance gap remained between frozen and fine-tuned encoders. In this work, we introduce methods that significantly strengthen zero-shot feature extraction for time series. First, we introduce Mantis+, a variant of Mantis pre-trained entirely […]

Ver mais

arXiv:2602.17867v1 Announce Type: new Abstract: Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maximally activate a target direction, offers an alternative to costly dataset search approaches, but remains underexplored for LLMs due to the discrete nature of text. Furthermore, existing prompt optimization techniques are poorly suited to this domain, which is highly prone to local minima. To overcome these limitations, we […]

Ver mais

arXiv:2602.17865v1 Announce Type: new Abstract: Time-series forecasting is a critical task across many domains, from engineering to economics, where accurate predictions drive strategic decisions. However, applying advanced deep learning models in challenging, volatile domains like finance is difficult due to the inherent limitation and dynamic nature of financial time series data. This scarcity often results in sub-optimal model training and poor generalization. The fundamental challenge lies in determining how to reliably augment scarce financial time series data to […]

Ver mais

arXiv:2602.17864v1 Announce Type: new Abstract: Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to assist, but we know little about how proactive agents affect the dynamics of real-time, co-located teamwork. We studied two forms of proactive support in digital escape rooms: a facilitator agent that offered summaries and group structures, and a peer agent that proposed ideas and answered queries. In […]

Ver mais